© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87214
    Prev
    Next
    INDEX
    Explanations

    contact fields and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    외부
    -0.90
    Toponymie
    -0.79
     mendat
    -0.77
    趋势
    -0.72
     facie
    -0.72
    gré
    -0.71
    outines
    -0.71
    edere
    -0.70
     endroit
    -0.70
    eward
    -0.70
    POSITIVE LOGITS
     message
    2.34
    message
    1.98
    getMessage
    1.70
     Message
    1.67
    Message
    1.63
     messages
    1.52
     subject
    1.38
     your
    1.35
     msg
    1.27
    MESSAGE
    1.24
    Activations Density 0.026%

    No Known Activations